{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0012504220174308829, "eval_steps": 13, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.500844034861766e-05, "eval_loss": 3.1160595417022705, "eval_runtime": 223.0739, "eval_samples_per_second": 37.741, "eval_steps_per_second": 18.873, "step": 1 }, { "epoch": 0.00025008440348617657, "grad_norm": 6.852118968963623, "learning_rate": 0.0002, "loss": 2.7499, "step": 10 }, { "epoch": 0.00032510972453202955, "eval_loss": 2.327143907546997, "eval_runtime": 223.4772, "eval_samples_per_second": 37.673, "eval_steps_per_second": 18.839, "step": 13 }, { "epoch": 0.0005001688069723531, "grad_norm": 6.103735446929932, "learning_rate": 0.0002, "loss": 2.3802, "step": 20 }, { "epoch": 0.0006502194490640591, "eval_loss": 2.205092191696167, "eval_runtime": 223.9454, "eval_samples_per_second": 37.594, "eval_steps_per_second": 18.799, "step": 26 }, { "epoch": 0.0007502532104585297, "grad_norm": 4.003726005554199, "learning_rate": 0.0002, "loss": 2.0594, "step": 30 }, { "epoch": 0.0009753291735960887, "eval_loss": 2.1543338298797607, "eval_runtime": 223.7647, "eval_samples_per_second": 37.624, "eval_steps_per_second": 18.814, "step": 39 }, { "epoch": 0.0010003376139447063, "grad_norm": 4.646275043487549, "learning_rate": 0.0002, "loss": 2.094, "step": 40 }, { "epoch": 0.0012504220174308829, "grad_norm": 6.49905252456665, "learning_rate": 0.0002, "loss": 2.0756, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1369718920839168.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }